TransBidiFilter:Knowledge Embedding Based on a Bidirectional Filter
A large-scale knowledge base can support a large number of practical applications,such as intelligent search and intelligent question answering.As the completeness of the information in a knowledge base may have a direct impact on the quality of downstream applications,its automatic completion has become a crucial task for many researchers and practitioners.To address this challenge,the knowledge representa-tion learning technology which represents entities and relations as low-dimensional dense real value vectors has been developed rapidly in recent years.Although researchers continue to improve knowledge representa-tion learning models using an increasingly complex feature engineering,we find that the most advanced models can be outdone by simply con-sidering interactions from entities to relations and that from relations to entities without requiring huge number of parameters.In this work,we present a knowledge embedding model based on a bidirectional filter called TransBidiFilter.By learning the global shared parameter set based on the traditional gate structure,TransBidiFilter captures the restric-tion rules from entities to relations and that from relations to entities respectively.It achieves better automatic completion ability by modi-fying the standard translation-based loss function.In doing so,though with much fewer discriminate parameters,TransBidiFilter performs bet-ter than state-of-the-art baselines of semantic discriminate models on most indicators on many datasets.
Knowledge representation Entity-based gate Relation-based gate
Xiaobo Guo Neng Gao Jun Yuan Lin Zhao Lei Wang Sibo Cai
Institute of Information Engineering,Chinese Academy of Sciences,Beijing,China;School of Cyber Secur Institute of Information Engineering,Chinese Academy of Sciences,Beijing,China College of Traffic Engineering,Hunan University of Technology,Zhuzhou,China Beijing Internetware Limited Corporation,Beijing,China
国际会议
9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)
郑州
英文
232-243
2020-10-14（万方平台首次上网日期，不代表论文的发表时间）